Caustics produce beautiful and intriguing illumination patterns. However, their complex behavior make them difficult to simulate accurately in all but the simplest configurations....
Reliably recovering 3D human pose from monocular video requires models that bias the estimates towards typical human poses and motions. We construct priors for people tracking usi...
We present a novel, efficient, initializationfree approach to the problem of epipolar geometry estimation, by formulating it as one of hyperplane inference from a sparse and noisy...
We describe a novel method for discovering and incorporating higher level map structure in a real-time visual SLAM system. Previous approaches use sparse maps, populated by isolate...
Andrew P. Gee, Denis Chekhlov, Andrew Calway, Walt...
We develop a robust technique to find similar matches of human actions in video. Given a query video, Motion History Images (MHI) are constructed for consecutive keyframes. This i...